Video Question Answering on LongVideoBench 1.0 (test)
67.2AccuracyMiMo-VL-7B + TCS
Evaluation Results
| Method | Links | |
|---|---|---|
| MiMo-VL-7B + TCS#Frames=322026.01 | 67.2 | |
| MiMo-VL-7B#Frames=322026.01 | 64.3 | |
| Qwen2-VL-7B + TCS#Frames=322026.01 | 60.9 | |
| Qwen2-VL-7B + AKS#Frames=322026.01 | 60.5 | |
| Qwen2-VL-7B + Q-Frame#Frames=4+8+322026.01 | 58.4 | |
| Qwen2-VL-7B#Frames=322026.01 | 55.5 |